Curve-based Neural Style Transfer
This work addresses a specific problem in product design by improving style transfer for design sketches, though it appears incremental as it builds on existing neural style transfer methods.
The paper tackles the challenge of applying neural style transfer to binary sketch transformations by introducing a parametric framework that uses shape-editing rules and fine-tuned VGG19, achieving enhanced style extraction for curve-based design sketches.
This research presents a new parametric style transfer framework specifically designed for curve-based design sketches. In this research, traditional challenges faced by neural style transfer methods in handling binary sketch transformations are effectively addressed through the utilization of parametric shape-editing rules, efficient curve-to-pixel conversion techniques, and the fine-tuning of VGG19 on ImageNet-Sketch, enhancing its role as a feature pyramid network for precise style extraction. By harmonizing intuitive curve-based imagery with rule-based editing, this study holds the potential to significantly enhance design articulation and elevate the practice of style transfer within the realm of product design.